.png){kind=icon}
返回
A Context Encoder For Audio Inpainting
.png){kind=icon}
PRE
AI
DOI：10.1109/TASLP.2019.2947232.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this article, we study the ability of deep neural networks (DNNs) to restore missing audio content based on its context, i.e., inpaint audio gaps. We focus on a condition which has not received much attention yet: gaps in the range of tens of milliseconds. We propose a DNN structure that is provided with the signal surrounding the gap in the form of time-frequency (TF) coefficients. Two DNNs with either complex-valued TF coefficient output or magnitude TF coefficient output were studied by separately training them on inpainting two types of audio signals (music and musical instruments) having 64-ms long gaps. The magnitude DNN outperformed the complex-valued DNN in terms of signal-to-noise ratios and objective difference grades. Although, for instruments, a reference inpainting obtained through linear predictive coding performed better in both metrics, it performed worse than the magnitude DNN for music. This demonstrates the potential of the magnitude DNN, in particular for inpainting signals that are more complex than single instrument sounds.
Keyword:
Instruments
Time-domain analysis
Music
Image reconstruction
Reliability
Prediction algorithms
Psychoacoustic models
Music
machine learning
frequency-domain analysis
signal processing algorithms
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Mixed-dimensional heterojunction by 3D CdS nanowire arrays bridged with 2D WSe2 for ultrafast photoelectric gas sensor.png)
MATTER
OAAI
MATTERIF17.5
OAAI分享收藏分享收藏分享收藏
查看更多内容